codex-claude-bridge vs filesystem

Side-by-side comparison to help you pick between these two MCP servers.

	codex-claude-bridge by abhishekgahlot2	filesystem by modelcontextprotocol
Stars	★ 38	★ 85,748
30d uses	—	—
Score	42	77
Official	—	✓
Categories	AI / LLM ToolsDeveloper ToolsCommunication	File SystemDeveloper ToolsProductivity
Language	TypeScript	TypeScript
Last commit	2 mo ago	this month

codex-claude-bridge · Summary

Bidirectional bridge between Claude Code and OpenAI Codex CLI using MCP and Claude Code Channels.

filesystem · Summary

A feature-rich MCP server for filesystem operations with dynamic directory access control.

codex-claude-bridge · Use cases

Enabling conversation between Claude Code and Codex CLI to combine their respective strengths
Creating a coding environment where two AI agents can collaborate on problems
Monitoring and potentially moderating a conversation between two AI coding assistants

filesystem · Use cases

Enable AI models to read and write project files during development
Allow Claude or other MCP clients to browse and analyze codebases
Provide secure sandboxed access to specific directories for content generation

codex-claude-bridge · Install

# Clone and install
git clone https://github.com/abhishekgahlot2/codex-claude-bridge.git
cd codex-claude-bridge
bun install

# Register with Claude Code
# Add to ~/.mcp.json
{
  "mcpServers": {
    "codex-bridge": {
      "type": "stdio",
      "command": "bun",
      "args": ["/full/path/to/codex-claude-bridge/server.ts"]
    }
  }
}

# Register with Codex CLI
# Add to ~/.codex/config.toml
[mcp_servers.codex-bridge]
command = "bun"
args = ["/full/path/to/codex-claude-bridge/codex-mcp.ts"]
tool_timeout_sec = 120

# Start Claude Code
claude --dangerously-load-development-channels server:codex-bridge

# Start Codex CLI
codex

Open http://localhost:8788 to view the conversation in the web UI.

filesystem · Install

Installation

Using NPX

{
  "mcpServers": {
    "filesystem": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-filesystem",
        "/path/to/allowed/directory"
      ]
    }
  }
}

Using Docker

{
  "mcpServers": {
    "filesystem": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "--mount", "type=bind,src=/path/to/allowed/dir,dst=/projects/allowed/dir",
        "mcp/filesystem",
        "/projects"
      ]
    }
  }
}

VS Code Extension

Click the installation buttons in the README to install directly in VS Code.

Comparison generated from public README + GitHub signals. Last updated automatically.